# Parallel/ Concurrent request with vLLM
**URL:**
**Author:**  [@Steax93](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSteax93)%5C
**Post date:** [July 3, 2024, 3:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparallel-concurrent-request-with-vllm%2F95359%2F1 "2024-07-03T15:06:32Z")
My question might be a bit basic, but I’m new to all of this and eager to learn.
I have a basic setup where I initialize an LLM using vLLM with Langchain RAG and the Llama model (specifically, llama2-13b-chat-hf). Here’s what I do:
- I define a system prompt and an instruction f
- I create an `llm_chain`
- I then run the chain with `llm_chain.run(text)` , which works for a single input.
I have build an app with FastAPI. Previously I used asyncio method to handle multiple request to llm, but with each new request it become slower in response. So I decide to use vLLM method, but I got a problem now how to provide parallel or concurrent requests to vLLM when I have dealing with dozen or more users. Is there a way to call `run` in parallel for several inputs and receive valid results for each input?
---
**Author:**  [@Magesh78](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMagesh78)%5C
**Post date:** [July 22, 2024, 7:33am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparallel-concurrent-request-with-vllm%2F95359%2F2 "2024-07-22T07:33:32Z")
Hi,
Have you got solutions for it?
---
**Author:**  [@ashish12345](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fashish12345)%5C
**Post date:** [November 27, 2024, 6:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparallel-concurrent-request-with-vllm%2F95359%2F3 "2024-11-27T06:13:36Z")
Hii, Have you got any solution for the same. I am also facing the same issues.
---
**Author:**  [@Steax93](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSteax93)%5C
**Post date:** [November 27, 2024, 10:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fparallel-concurrent-request-with-vllm%2F95359%2F4 "2024-11-27T10:12:44Z")
Hello unfortunately no, so decide to move on without vLLM.